Classification of keywords

Abstract

A computer-implemented method of classifying a keyword in a network comprises: identifying a plurality of candidate categories, comprising: converting a plurality of search results related to the keyword into a plurality of search vectors, wherein each of the plurality of search results indicates a related resource in the network; converting a plurality of resources into a plurality of category vectors, wherein each of the plurality of resources is classified in one or more categories of a set of categories; and determining, for the plurality of category vectors, a plurality of similarity values indicating similarity to the plurality of search vectors; processing the plurality of candidate categories; and classifying the keyword by selecting the candidate category having a highest similarity value within the plurality of similarity values, a corresponding system, computing device and non-transitory computer-readable storage medium.

Description

BACKGROUND OF THE INVENTION[0001]Field of the Invention[0002]The invention relates to a method, system, computing device and storage medium for classifying keywords, i.e. tagging or labelling keywords with categories. More specifically, the invention relates to a method, system, computing device and storage medium for classifying keywords for resources in a network.[0003]Background of the Invention[0004]The World-Wide Web (www) comprises an indefinite number of webpages. Search engines crawl the webpages via the Internet and return, for user convenience, a list of webpages relevant to any particular search term, i.e. one or more keywords. Operators aiming to promote their webpages onto these lists of webpages create and optimize, using various techniques, their webpages for the search engines (search engine optimization, SEO). Recently, access to and usage of the World-Wide Web has moved from stationary personal computers to mobile computing devices, which adds another layer of comp...

AI Technical Summary

Benefits of technology

The present invention provides a method and computing device for identifying relevant terms and categories associated with search results or resources. This can be useful for controlling the classification of keywords and search queries, even if technical or financial means are limited. The invention can also enable users to save time and reduce costs by focusing on particular keywords and search queries. The technique involves extracting relevant terms, removing irrelevant terms, producing word embeddings, reducing vector dimensionality, and selecting relevant categories based on similarity values. The technical effects of the invention are improved control over keyword and search query classification, improved efficiency, and improved cost-effectiveness.

Problems solved by technology

Recently, access to and usage of the World-Wide Web has moved from stationary personal computers to mobile computing devices, which adds another layer of complexity to search engine optimization.

Owing to the indefinite number of webpages and their ever changing contents, it is increasingly difficult to understand and match the users' search intention and / or buying cycle for a particular search query, and to get resources highly ranked by search engines in organic search results for relevant keywords.

Images